Catapult case
Six Sigma – iSixSigma › Forums › Old Forums › General › Catapult case
- This topic has 12 replies, 7 voices, and was last updated 13 years, 2 months ago by
Severino.
-
AuthorPosts
-
April 22, 2009 at 10:35 am #52239
Hi,
Anybody have a Catapult excercise case that covers MSA, Capability, Multivari, Anova, DOE.
And wants to share it ;-)
Jan0April 23, 2009 at 4:44 am #183633
Jonathan LeaheyParticipant@Jonathan-LeaheyInclude @Jonathan-Leahey in your post and this person will
be notified via email.Jan:Are you looking for PPT instructions? When I’m training, I just run all of these matters informally, by setting up teams and factors in Minitab on the fly.MSA can be done a number of ways, but there are probably better exercises for GR&R, if that’s what you are trying to tackle. AAA can be done by using the catapult with observers, but since the catapult exercise is a “destructive test” it’s impossible to get repeatibility.If you want to chat about all of this, drop me a line and a number.Warm regards,Jonathan Leahey
Pres. LCG, LLC0April 23, 2009 at 6:46 am #183638Thanks for your reply.
No I am not seeking ppt. But a good case story.
I am working on a WB training for R&D managers.
Jan0April 23, 2009 at 11:29 am #183647
KluttzMember@Union-of-Conjoined-ScientistsInclude @Union-of-Conjoined-Scientists in your post and this person will
be notified via email.Its not impossible to get repeatibility
0April 24, 2009 at 2:51 am #183677Jonathan,
Please educate me as to why the catapult DOE would need to be destructive. I can think of scenarios where the “missile” can be retrievable and therefore repeatability should be possible.
Cyrus0April 24, 2009 at 4:44 am #183680
Jonathan LeaheyParticipant@Jonathan-LeaheyInclude @Jonathan-Leahey in your post and this person will
be notified via email.Cyrus:Perhaps I wasn’t clear. If you read my missive, what I was saying is that you would be hard pressed to do measurement systems analysis with the catapult.Why? If you were using observers to record where the ball landed to compare their results, you couldn’t replicate the ball landing in the same exact spot every shot. If you argue that you can, I would surmise that your measurement system lacks discrimination.I’ve done several DOE’s with catapults of all sorts. That shouldn’t be a problem. In fact, if you use Mintab’s byzantine structure to set up a GFF, FF, etc., the exercise is a great way to select factors and take a class through the data set-up protocol.Hope this helps.Let me know if I can be of further assistance.Regards,
Jonathan0April 24, 2009 at 11:53 am #183684
KluttzMember@Union-of-Conjoined-ScientistsInclude @Union-of-Conjoined-Scientists in your post and this person will
be notified via email.A major component of any project (simulated or other wise) is the need to develop an accurate measurement system. I think if you’re relying on people trying to eyeball where the ball lands, you’re overlooking a key point of the exercise. It’s not just about the use of tools and lean concepts. Its about identifying and eliminating as many potential contributors to variations as possible. And measurement system variation is part of that.
There are a thousand different ways to get an accurate measurement every single time without the parallax error of eyeball judgment. For $16,200 I’ll send you the one that I used.0April 24, 2009 at 12:57 pm #183685
MrMHeadParticipant@MrMHeadInclude @MrMHead in your post and this person will
be notified via email.We used aluminum foil in the target area to get the mark of the projectile landing. Then the MSA had to include the operational definition of how to measure (front of dent?, middle, back ..etc) to ensure consistency.
M0April 24, 2009 at 1:40 pm #183686MrMH:We settled on the same procedure with aluminum foil, but only after an informal rejection of the eye-ball method as unreliable.Our discussion of MSA tends to center on operational definitions such as measuring the front/center/middle of the dent.Cheers, Alastair
0April 24, 2009 at 2:15 pm #183687
KluttzMember@Union-of-Conjoined-ScientistsInclude @Union-of-Conjoined-Scientists in your post and this person will
be notified via email.When I did the catapult exercise, are final target was a coffee cup placed at the prescribed distance. So the aluminum foil method wouldn’t work since we had to factor in the elevation and circumference of the cup’s rim. We ended up getting a 10 ft length of plastic gutter liner (approximately the same diameter as the cup) and filling it to the appropriate height with sand. That way we could determine preceisely where the ball would hit the rim.
0April 24, 2009 at 3:28 pm #183689
MrMHeadParticipant@MrMHeadInclude @MrMHead in your post and this person will
be notified via email.So you had to take lateral precision into account as well!
I remember our shots weren’t in line and that was one of the challenges of the MSA/ OD. Do we measure from a point (center of cat base) or from a line parallel to the front?
Recently saw a show on History Channel, Ancient Weapons (?), about catapults and trebuchets . . brought back fond memories. Only we didn’t get to launch pumpkins and bowling balls.0April 24, 2009 at 3:46 pm #183691
KluttzMember@Union-of-Conjoined-ScientistsInclude @Union-of-Conjoined-Scientists in your post and this person will
be notified via email.As far as the off center problem went, we affixed a laser level to the front of the catapult for both aiming and aligning purposes. Using the laser as the centerpoint, you could draw parallel lines 2″ or so on either side to measure lateral accuracy as well as distance accuracy. It would also be important to secure the catapult so its not drifting shot to shot.
0April 25, 2009 at 2:06 am #183697
SeverinoParticipant@Jsev607Include @Jsev607 in your post and this person will
be notified via email.I found an article that utilizes Shainin Variable Search for the catapult. I found it quite interesting. Has anyone ever seen a justification for the 1.25:1 ratio or is this like the 1.5 sigma shift?
0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.